Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964247925> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2964247925 endingPage "250" @default.
- W2964247925 startingPage "241" @default.
- W2964247925 abstract "We consider the problem of boosting the accuracy of weak learning algorithms in the agnostic learning framework of Haussler (1992) and Kearns et al. (1992). Known algorithms for this problem (Ben-David et al., 2001; Gavinsky, 2002; Kalai et al. , 2008) follow the same strategy as boosting algorithms in the PAC model: the weak learner is executed on the same target function but over different distributions on the domain. Application of such boosting algorithms usually requires a distribution-independent weak agnostic learners. Here we demonstrate boosting algorithms for the agnostic learning framework that only modify the distribution on the labels of the points (or, equivalently, modify the target function). This allows boosting a distribution-specific weak agnostic learner to a strong agnostic learner with respect to the same distribution. Our algorithm achieves the same guarantees on the final error as the boosting algorithms of Kalai et al. (2008) but is substantially simpler and more efficient. When applied to the weak agnostic parity learning algorithm of Goldreich and Levin (1989) our algorithm yields a simple PAC learning algorithm for DNF and an agnostic learning algorithm for decision trees over the uniform distribution using membership queries. These results substantially simplify Jackson’s famous DNF learning algorithm (1994) and the recent result of Gopalan et al. (2008). We also strengthen the connection to hard-core set constructions discovered by Klivans and Servedio (1999) by demonstrating that hard-core set constructions that achieve the optimal hard-core set size (given by Holenstein (2005) and Barak et al. (2009)) imply distribution-specific agnostic boosting algorithms. Conversely, our boosting algorithm gives a simple hard-core set construction with an (almost) optimal hard-core set size." @default.
- W2964247925 created "2019-07-30" @default.
- W2964247925 creator A5054675941 @default.
- W2964247925 date "2010-01-01" @default.
- W2964247925 modified "2023-09-23" @default.
- W2964247925 title "Distribution-Specific Agnostic Boosting" @default.
- W2964247925 cites W1534925209 @default.
- W2964247925 cites W1536299660 @default.
- W2964247925 cites W1548189207 @default.
- W2964247925 cites W1570592793 @default.
- W2964247925 cites W1605688901 @default.
- W2964247925 cites W1968540673 @default.
- W2964247925 cites W1976697079 @default.
- W2964247925 cites W1982381767 @default.
- W2964247925 cites W1988790447 @default.
- W2964247925 cites W1995055819 @default.
- W2964247925 cites W1995897489 @default.
- W2964247925 cites W2003866851 @default.
- W2964247925 cites W2016201895 @default.
- W2964247925 cites W2019363670 @default.
- W2964247925 cites W2026103826 @default.
- W2964247925 cites W2027528470 @default.
- W2964247925 cites W2063083207 @default.
- W2964247925 cites W2064680241 @default.
- W2964247925 cites W2075412780 @default.
- W2964247925 cites W2080210666 @default.
- W2964247925 cites W2084544490 @default.
- W2964247925 cites W2088390444 @default.
- W2964247925 cites W2093717447 @default.
- W2964247925 cites W2095546965 @default.
- W2964247925 cites W2098933520 @default.
- W2964247925 cites W2106458073 @default.
- W2964247925 cites W2119243017 @default.
- W2964247925 cites W2121618740 @default.
- W2964247925 cites W2130246629 @default.
- W2964247925 cites W2142399242 @default.
- W2964247925 cites W2147306258 @default.
- W2964247925 cites W2150458133 @default.
- W2964247925 cites W2160403361 @default.
- W2964247925 cites W2914930992 @default.
- W2964247925 hasPublicationYear "2010" @default.
- W2964247925 type Work @default.
- W2964247925 sameAs 2964247925 @default.
- W2964247925 citedByCount "11" @default.
- W2964247925 countsByYear W29642479252012 @default.
- W2964247925 countsByYear W29642479252013 @default.
- W2964247925 countsByYear W29642479252014 @default.
- W2964247925 countsByYear W29642479252015 @default.
- W2964247925 countsByYear W29642479252020 @default.
- W2964247925 countsByYear W29642479252021 @default.
- W2964247925 crossrefType "proceedings-article" @default.
- W2964247925 hasAuthorship W2964247925A5054675941 @default.
- W2964247925 hasConcept C11413529 @default.
- W2964247925 hasConcept C119857082 @default.
- W2964247925 hasConcept C154945302 @default.
- W2964247925 hasConcept C33923547 @default.
- W2964247925 hasConcept C41008148 @default.
- W2964247925 hasConcept C46686674 @default.
- W2964247925 hasConcept C80444323 @default.
- W2964247925 hasConceptScore W2964247925C11413529 @default.
- W2964247925 hasConceptScore W2964247925C119857082 @default.
- W2964247925 hasConceptScore W2964247925C154945302 @default.
- W2964247925 hasConceptScore W2964247925C33923547 @default.
- W2964247925 hasConceptScore W2964247925C41008148 @default.
- W2964247925 hasConceptScore W2964247925C46686674 @default.
- W2964247925 hasConceptScore W2964247925C80444323 @default.
- W2964247925 hasOpenAccess W2964247925 @default.
- W2964247925 hasRelatedWork W1536601806 @default.
- W2964247925 hasRelatedWork W1548189207 @default.
- W2964247925 hasRelatedWork W1982381767 @default.
- W2964247925 hasRelatedWork W1995897489 @default.
- W2964247925 hasRelatedWork W2019363670 @default.
- W2964247925 hasRelatedWork W2063083207 @default.
- W2964247925 hasRelatedWork W2084544490 @default.
- W2964247925 hasRelatedWork W2088390444 @default.
- W2964247925 hasRelatedWork W2098933520 @default.
- W2964247925 hasRelatedWork W2099362736 @default.
- W2964247925 hasRelatedWork W2106458073 @default.
- W2964247925 hasRelatedWork W2117756453 @default.
- W2964247925 hasRelatedWork W2121618740 @default.
- W2964247925 hasRelatedWork W2130246629 @default.
- W2964247925 hasRelatedWork W2135481450 @default.
- W2964247925 hasRelatedWork W2147306258 @default.
- W2964247925 hasRelatedWork W2149840272 @default.
- W2964247925 hasRelatedWork W2186076924 @default.
- W2964247925 hasRelatedWork W3208595835 @default.
- W2964247925 hasRelatedWork W2584920103 @default.
- W2964247925 isParatext "false" @default.
- W2964247925 isRetracted "false" @default.
- W2964247925 magId "2964247925" @default.
- W2964247925 workType "article" @default.